© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33393
    Prev
    Next
    INDEX
    Explanations

    when following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıĺ缸
    -0.07
    .VisualStudio
    -0.07
    esion
    -0.06
    enko
    -0.06
     Anders
    -0.06
    ishes
    -0.06
    .tif
    -0.06
    åĨįä¸į
    -0.06
    人家
    -0.06
    STYPE
    -0.06
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥äºĨ解
    0.09
    ä»Ĭ度ãģ¯
    0.09
    è¿Ľä¸ĢæŃ¥
    0.09
     further
    0.08
    æĪij们è¿ĺåı¯ä»¥
    0.08
    è¿Ľä¸ĢæŃ¥æıIJåįĩ
    0.08
     weiteren
    0.08
    å±±é«ĺ
    0.08
    éĢ²ä¸ĢæŃ¥
    0.07
    æĪij们è¿ĺ
    0.07
    Activations Density 0.366%

    No Known Activations